AI agents call sg_acra_get_entity to retrieve information from Sgdata without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a simple lookup of publicly available Singapore corporate entity data by unique entity number (UEN). It retrieves information only and has no side effects, reversible modifications, code execution, or financial implications. The blast radius of misuse is minimal since it only returns existing public corporate registry data. Classified as Read with low severity.
From the tool's definition Tool description states 'Look up a single ACRA corporate entity by exact UEN via a server-side' - this is a query/retrieval operation that returns public corporate registration data without modifying, deleting, or executing external operations.
Attacks that exploit this kind of access
Look up a single ACRA corporate entity by exact UEN via a server-side. It is categorised as a Read tool in the Sgdata MCP Server, which means it retrieves data without modifying state.
Register the Sgdata MCP server in PolicyLayer and add a rule for sg_acra_get_entity: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Sgdata. Nothing to install.
sg_acra_get_entity is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the sg_acra_get_entity rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for sg_acra_get_entity. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
sg_acra_get_entity is provided by the Sgdata MCP server (sypherin/sgdata-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →